Documentation

Errors / Rate limits

Errors

HTTP errors have an error object with code and message. A successfully accepted task can still fail later; query the task or handle its failure callback.

{
  "error": {
    "code": "invalid_request",
    "message": "input.prompt is required."
  }
}

HTTP	Field	What to do
400	`invalid_request`	Fix the JSON, missing prompt, parameter range or media URL before retrying.
401	`invalid_api_key`	Check the Bearer token and whether the API key is active.
402	`insufficient_credits`	Add credits or reduce the task cost. The response may include required and available amounts.
403	`forbidden`	Check the account-level restriction described in the error message.
404	`not_found`	Check the task ID and that the key belongs to the task's user.
429	`rate_limited`	Wait for the Retry-After interval before retrying.
500	`internal_error`	Inspect the error message and API logs. Retry cautiously; resubmitting a create request can create another billable task.

Rate limits

Create tasks: each API key allows up to 100 requests per minute by default. Custom rate limits are not currently available.

Query tasks: each API key allows up to 120 requests per minute by default. Query requests and task creation requests are counted separately.

Image and video creation requests share the same API key rate limit.

HTTP 429 includes Retry-After: 60 for creation and Retry-After: 5 for queries. Use backoff and avoid polling more frequently than necessary.

HTTP/1.1 429 Too Many Requests
Content-Type: application/json
Retry-After: 60

{
  "error": {
    "code": "rate_limited",
    "message": "Rate limit exceeded."
  }
}